AI in IT Operations Management
Summarize
Summary of AI in IT Operations Management
AI in IT Operations Management (ITOM) leverages generative AI and agentic workflows to assist operators in triaging alerts, investigating incidents, automating service mapping, diagnosing infrastructure, and generating resolution artifacts. The ServiceNow AI Platform offers three licensing tiers—Foundation, Advanced, and Prime—each providing progressively advanced AI capabilities ranging from basic insights to autonomous actions and custom AI asset creation.
Show less
Key Features
- AI Licensing Tiers: Foundation delivers basic AI insights; Advanced enhances productivity for relevant use cases; Prime enables autonomous operations and creation of AI assets.
- AI Features by ITOM Product: Includes capabilities in Discovery, Service Mapping, Firewall Audits, Certificate Management, LEAP ITOM, AIOps, Express List, Service Observability, SLO Management, and Agent Client Collector Monitoring.
- AI Model Providers: Supports Now LLM Service, Azure OpenAI, Google Gemini, and Anthropic Claude on AWS. Availability depends on customer region and licensing. Configuration is managed via AI Control Tower and AI Admin Hub.
- Security and Access Control: AI agents and workflows use Access Control Lists (ACLs) and user identities, configurable in AI Agent Studio, ensuring secure operation within user permissions.
- Domain Separation: AI skills operate within domain boundaries, ensuring data access and AI-generated outputs are confined to users’ specific domains without data co-mingling across domains or persistence outside the instance.
- Data Handling and Privacy: Data from instances may be transferred to centralized ServiceNow environments or third-party cloud providers following internal policies. Customers can opt out of data collection used to improve AI models.
- Installed Agents: Instances may have AI agents installed beyond those used in agentic workflows; customers can view available agents to manage usage effectively.
Considerations and Limitations
- AI-generated outputs may not always be accurate or complete; customers must test and validate AI results, especially in critical domains such as healthcare, finance, or security.
- Human oversight is essential; decisions should not rely solely on AI outputs.
- ServiceNow’s AI Acceptable Use Policy governs responsible AI use and may be updated over time.
- Some AI features are unavailable in specific regulated markets, data centers, or regions; customers should verify availability for their environments.
Getting Support
- Access the ServiceNow Community focused on AI and Intelligence for discussions and shared knowledge.
- Consult the Known Error Portal for troubleshooting known issues.
- Contact ServiceNow Customer Service and Support for personalized assistance.
AI features across IT Operations Management help operators triage alerts, investigate incidents, automate service mapping, diagnose infrastructure, and generate resolution artifacts using generative AI and agentic workflows.
- Foundation: AI basics to deliver insights
- Advanced: AI to boost productivity across relevant use cases
- Prime: Act autonomously with all AI assets, and create your own
ITOM Visibility
For a summary of all AI features across ITOM Visibility, see AI in ITOM Visibility.
For AI features by product, see the following topics:
ITOM AIOps
For a summary of all AI features across ITOM AIOps, see AI in ITOM AIOps.
For AI features by product, see the following topics:
AI model providers
You can use Now LLM Service, Azure OpenAI, Google Gemini or Anthropic Claude on AWS as the AI model provider for all generative AI skills and AI agents. Use the Configuration Controls in AI Control Tower to define which options are available, then set the skill-level preferences in the AI Admin Hub console. For more information, see Large language models on the ServiceNow AI Platform®.
- Not all model providers are available for customers with in-country SKUs, and some AI products/features are currently unavailable for in-country customers. For more information, see the KB1584492 article in the Now Support Knowledge Base. Be sure to check for model provider availability updates in future releases.
- Some AI products/features are currently unavailable for customers in the FedRAMP, NSC DOD IL5, or Australia IRAP-Protected data centers, self-hosted customers, or in other restricted environments. For more information, see the KB0743854 article in the Now Support Knowledge Base. Be sure to check for availability updates in future releases.
- Some AI products/features are currently available only for customers in some regions. Be sure to check for availability updates in future releases.
- Some AI products and skills are not available in Regulated Markets. For more information, see KB2593939: Regulated Markets AI Products/Skills Not Available. Be sure to check for availability updates in future releases.
Installed agents
There might be AI agents installed on your instance that are not used in agentic workflows. To learn how to see all agents that are available to you, see Find AI agents.
Security
Enable security settings to run AI agents and agentic workflows using Access Control Lists (ACLs) and user identities. You can configure and manage the ACLs in AI Agent Studio. See Implement access control in Now Assist AI agents for more information.
Dependencies
For a list of plugin dependencies, see Applications installed with ServiceNow Otto for ITOM.
Domain separation and generative AI
By default, all skills exist in the global domain. When you use AI in a domain-separated environment, users are only able to access data in their domain. For example, if a user uses the summarization skill, AI only uses material that exists in the user's domain when generating that summary. Additionally, there is no co-mingling of data for domain-separated instances when using generative AI skills. The data resides only on the instance, and the shared services used for generative AI do not persist any requests (prompts) and responses. For more information, see Domain separation in the Now Assist Admin console. (Note that global domain is not the same as global scope. For more information, see Exploring Next Experience pickers.)
Data processing
This application requires data to be transferred from ServiceNow customers' individual instances to a centralized ServiceNow environment, which may be located in a different data center region from the one where your instance is, and potentially to a third-party cloud provider, such as Microsoft Azure. This data is handled per ServiceNow's internal policies and procedures, including our policies available through our CORE Compliance Portal.
Data collection
ServiceNow collects and uses the inputs, outputs, and edits to outputs of this application to develop and improve ServiceNow technologies including ServiceNow models and AI products. Customers can opt out of future data collection at any time, as described in the Now Assist Opt-Out page.
AI limitations
This application uses artificial intelligence (AI) and machine learning, which are rapidly evolving fields of study that generate predictions based on patterns in data. As a result, this application may not always produce accurate, complete, or appropriate information. Furthermore, there is no guarantee that this application has been fully trained or tested for your use case. To mitigate these issues, it is your responsibility to test and evaluate your use of this application for accuracy, harm, and appropriateness for your use case, employ human oversight of output, and refrain from relying solely on AI-generated outputs for decision-making purposes. This is especially important if you choose to deploy this application in areas with consequential impacts such as healthcare, finance, legal, employment, security, or infrastructure. You agree to abide by ServiceNow’s AI Acceptable Use Policy, which may be updated by ServiceNow.